CN106993226A - A kind of method and terminal of recommendation video - Google Patents
A kind of method and terminal of recommendation video Download PDFInfo
- Publication number
- CN106993226A CN106993226A CN201710164492.1A CN201710164492A CN106993226A CN 106993226 A CN106993226 A CN 106993226A CN 201710164492 A CN201710164492 A CN 201710164492A CN 106993226 A CN106993226 A CN 106993226A
- Authority
- CN
- China
- Prior art keywords
- video file
- interest
- video
- terminal
- decomposed
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Withdrawn
Links
- 238000000034 method Methods 0.000 title claims abstract description 33
- 238000000605 extraction Methods 0.000 claims abstract description 27
- 230000001537 neural effect Effects 0.000 claims description 18
- 238000010586 diagram Methods 0.000 description 15
- 239000000284 extract Substances 0.000 description 13
- 230000006870 function Effects 0.000 description 10
- 101100110009 Caenorhabditis elegans asd-2 gene Proteins 0.000 description 6
- 230000009471 action Effects 0.000 description 6
- 238000012545 processing Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 230000004044 response Effects 0.000 description 4
- 238000003860 storage Methods 0.000 description 4
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 239000003795 chemical substances by application Substances 0.000 description 2
- 238000012790 confirmation Methods 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 230000002452 interceptive effect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
- H04N21/466—Learning process for intelligent management, e.g. learning user preferences for recommending movies
- H04N21/4668—Learning process for intelligent management, e.g. learning user preferences for recommending movies for recommending content, e.g. movies
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/44—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream or rendering scenes according to encoded video stream scene graphs
- H04N21/44008—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream or rendering scenes according to encoded video stream scene graphs involving operations for analysing video streams, e.g. detecting features or characteristics in the video stream
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
- H04N21/466—Learning process for intelligent management, e.g. learning user preferences for recommending movies
- H04N21/4662—Learning process for intelligent management, e.g. learning user preferences for recommending movies characterized by learning algorithms
- H04N21/4666—Learning process for intelligent management, e.g. learning user preferences for recommending movies characterized by learning algorithms using neural networks, e.g. processing the feedback provided by the user
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the invention discloses a kind of method and terminal of recommendation video, wherein, methods described includes：Obtain the first interest information for the targeted customer for needing to obtain video information；The first video file of candidate is decomposed into the second video file, and the extraction interest element from second video file；Calculate the matching degree of the interest element and first interest information；If the matching degree meets preset requirement, first video file is recommended into the targeted customer, can be to the accurate recommended user of user video interested.
Description
Technical field
The present invention relates to electronic technology field, more particularly to a kind of method and terminal of recommendation video.
Background technology
In the prior art, the method for recommending video is typically the label information for pre-setting video file, is getting use
During the interest information at family, the matching degree of label information and the interest information of user is calculated, so as to obtain candidate video file and use
The matching degree of family interest, matching degree is met into preset requirement, and (matching degree highest video file or matching degree are more than preset matching
Spend threshold value) N number of video to user, N is the integer more than or equal to 1.Wherein, label information is used for the spy for identifying video file
Levy.
Because the method for recommending video in the prior art depends on the label information of video file, the accuracy of label information
Directly decide whether that suitable video file can be recommended for user.And in the prior art, it is impossible to precise marking label information, nothing
The accurate recommended user of normal direction user video interested.
The content of the invention
The embodiment of the present invention provides a kind of method and terminal of recommendation video, can be interested to the accurate recommended user of user
Video.
In a first aspect, the embodiments of the invention provide a kind of method of recommendation video, this method includes：
Obtain the first interest information for the targeted customer for needing to obtain video information；
The first video file of candidate is decomposed into the second video file, and interest is extracted from second video file
Element；
Calculate the matching degree of the interest element and first interest information；
If the matching degree meets preset requirement, first video file is recommended into the targeted customer.
On the other hand, the embodiments of the invention provide a kind of terminal, the terminal includes：
Acquiring unit, the first interest information for obtaining the targeted customer for needing to obtain video information；
Extraction unit, for the first video file of candidate to be decomposed into the second video file, and from second video
Interest element is extracted in file；
Computing unit, the matching degree for calculating the interest element and first interest information；
Recommendation unit, if meeting preset requirement for the matching degree, first video file is recommended described
Targeted customer.
The embodiment of the present invention needs to obtain the first interest information of the targeted customer of video information by acquisition；By candidate's
First video file is decomposed into the second video file, and the extraction interest element from second video file；Calculate described emerging
The matching degree of interesting element and first interest information；If the matching degree meets preset requirement, by first video text
Part recommends the targeted customer.Because terminal is that the first video file is decomposed into at least two the second short video files,
And the video image of the second video file is analyzed, the interest element that includes in video image is therefrom extracted, the can be accurately known
The corresponding interest element of one video file, so as to the accurate recommended user of user video interested.
Brief description of the drawings
Technical scheme, is used required in being described below to embodiment in order to illustrate the embodiments of the present invention more clearly
Accompanying drawing is briefly described, it should be apparent that, drawings in the following description are some embodiments of the present invention, general for this area
For logical technical staff, on the premise of not paying creative work, other accompanying drawings can also be obtained according to these accompanying drawings.
Fig. 1 is a kind of schematic flow diagram of the method for recommendation video provided in an embodiment of the present invention；
Fig. 2 is a kind of schematic flow diagram of the method for recommendation video that another embodiment of the present invention is provided；
Fig. 3 is a kind of schematic diagram of convolutional Neural net connected entirely provided in an embodiment of the present invention；
Fig. 4 extracts the schematic diagram of characteristic element in being a kind of figure from frame provided in an embodiment of the present invention；
Fig. 5 is a kind of signal for doing convolution to frame figure using default convolutional Neural net algorithm provided in an embodiment of the present invention
Figure；
Fig. 6 is the schematic diagram of a kind of interest element provided in an embodiment of the present invention and the first interest information；
Fig. 7 is a kind of schematic block diagram of terminal provided in an embodiment of the present invention；
Fig. 8 is a kind of terminal schematic block diagram that another embodiment of the present invention is provided；
Fig. 9 is a kind of terminal schematic block diagram that yet another embodiment of the invention is provided.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation is described, it is clear that described embodiment is a part of embodiment of the invention, rather than whole embodiments.Based on this hair
Embodiment in bright, the every other implementation that those of ordinary skill in the art are obtained under the premise of creative work is not made
Example, belongs to the scope of protection of the invention.
It should be appreciated that ought be in this specification and in the appended claims in use, term " comprising " and "comprising" be indicated
Described feature, entirety, step, operation, the presence of element and/or component, but be not precluded from one or more of the other feature, it is whole
Body, step, operation, element, component and/or its presence or addition for gathering.
It is also understood that the term used in this description of the invention is merely for the sake of the mesh for describing specific embodiment
And be not intended to limit the present invention.As used in description of the invention and appended claims, unless on
Other situations are hereafter clearly indicated, otherwise " one " of singulative, " one " and "the" are intended to include plural form.
It will be further appreciated that, the term "and/or" used in description of the invention and appended claims is
Refer to any combinations of one or more of the associated item listed and be possible to combination, and including these combinations.
As used in this specification and in the appended claims, term " if " can be according to context quilt
Be construed to " when ... " or " once " or " in response to determining " or " in response to detecting ".Similarly, phrase " if it is determined that " or
" if detecting [described condition or event] " can be interpreted to mean according to context " once it is determined that " or " in response to true
It is fixed " or " once detecting [described condition or event] " or " in response to detecting [described condition or event] ".
In the specific implementation, the terminal described in the embodiment of the present invention is including but not limited to such as with touch sensitive surface
The mobile phone, laptop computer or tablet PC of (for example, touch-screen display and/or touch pad) etc it is other just
Portable device.It is to be further understood that in certain embodiments, the equipment not portable communication device, but with touching
Touch the desktop computer of sensing surface (for example, touch-screen display and/or touch pad).
In discussion below, the terminal including display and touch sensitive surface is described.It is, however, to be understood that
It is that terminal can include one or more of the other physical user-interface device of such as physical keyboard, mouse and/or control-rod.
Terminal supports various application programs, such as one or more of following：Drawing application program, demonstration application journey
Sequence, word-processing application, website create application program, disk imprinting application program, spreadsheet applications, game application
Program, telephony application, videoconference application, email application, instant messaging applications, exercise
Support application program, photo management application program, digital camera application program, digital camera application program, web-browsing application
Program, digital music player application and/or video frequency player application program.
The various application programs that can be performed in terminal can use such as touch sensitive surface at least one is public
Physical user-interface device.It can adjust and/or change among applications and/or in corresponding application programs and touch sensitive table
The corresponding information shown in the one or more functions and terminal in face.So, the public physical structure of terminal is (for example, touch
Sensing surface) the various application programs with user interface directly perceived and transparent for a user can be supported.
Fig. 1 is referred to, Fig. 1 is a kind of schematic flow diagram of the method for recommendation video provided in an embodiment of the present invention.This reality
The executive agent for applying the method for recommending video in example is terminal, and terminal can play video.Terminal can be mobile phone, tablet personal computer
Deng mobile terminal, but this is not limited to, can also be other-end.The method of recommendation video as shown in Figure 1 may include following
Step：
S101：Obtain the first interest information for the targeted customer for needing to obtain video information.
Terminal is in normal work, and when detecting user's unlatching or triggering the function of recommending video, and terminal can be according to mesh
The mark of user is marked, the first interest information for the targeted customer for needing to obtain video information is obtained.
Wherein, user can recommend the function of video by setting interface to open, and can also pass through preassembled application
The function of video is recommended in the interactive interface triggering of program (Application, APP).The application program has according to the emerging of user
Interest hobby recommends the function of video.
The mark of targeted customer can be the title or the pet name of targeted customer or the electronic account of targeted customer
Deng can also be the mark (for example, the MAC Address of terminal device, but be not limited to this) for the terminal device that targeted customer uses
Deng not being limited herein.
Specifically, terminal can obtain the interest information of targeted customer from the personal information of targeted customer.For example, target
User fill in hobby information in corresponding " personal information " interactive interface of account of instant communications applications in advance, or
Personal interest preference information is pre-filled with e-survey Questionnaire systems, then terminal can be obtained according to the mark of targeted customer
Take the first interest information of targeted customer.
Terminal can also be according to the historical search data of targeted customer, the historical data analysis targeted customer that watches video
First interest information.
First interest information can include liking cartoon, like action movie, like certain star, like comedy, science and technology control
Deng one of them or at least two any combination, but be not limited to this, can be limited herein with other hobbies.
S102：The first video file of candidate is decomposed into the second video file, and carried from second video file
Take interest element.
Terminal obtains the first video file of candidate from video library, and the first video file is decomposed into at least two
Two video files, and the video image that each second video file is included is analyzed, extract interest from each second video file
Element.
Wherein, the first video file is any one in video library；What at least two second video files were included regards
Frequency image can be spliced into the first video file.Interest element is the characteristic information that can be identified for that hobby.
S103：Calculate the matching degree of the interest element and first interest information.
Terminal can enter the first interest information of the interest element extracted from the second video file and targeted customer
Row compares, to judge whether the interest element extracted is consistent with the first interest information of targeted customer, so as to obtain interest member
The matching degree of element and the first interest information of targeted customer.Matching degree can be percentage or specific fraction, herein
It is not limited.
For example, when the first interest information of targeted customer is comprising cartoon is liked, being extracted from the second video file
When interest element is cartoon element, the matching degree of the first interest information of terminal check interest element and targeted customer is
100%.
Like cartoon when the first interest information of targeted customer is included, like certain to sing star, from the second video file
In the interest element that extracts when being information (name or photograph of certain singer) of certain singer, terminal check interest element and target
The matching degree of the first interest information of user is 50%.
When the interest element extracted from the second video file does not include the first interest information of targeted customer, terminal
The matching degree for confirming interest element and the first interest information of targeted customer is zero, that is, the interest element extracted and the first interest
Information is mismatched.
When the first interest information at least two interest of correspondence of targeted customer, terminal can distribute weight to each interest
(can according to like degree to distribute weight), and confirming that the interest element that extracts includes corresponding of the first interest information
When interest is interesting, according to interest element and the weight of corresponding at least two interest of the first interest information, calculate interest element with
The matching degree of first interest information.
Wherein, terminal can like degree to distribute weight, happiness according to corresponding at least two interest of the first interest information
Joyous degree can be obtained from the search rate in historical viewing data or viewing number of times.
For example, when the first interest information of targeted customer includes " liking cartoon ", " liking certain to sing star ", " liking
The corresponding weight of cartoon " is 0.8, and " liking certain to sing star " corresponding weight is 0.2, is extracted from the second video file
Interest element when singing information (name or photograph of certain singer) of singer for certain, terminal check interest element and targeted customer
The first interest information matching degree be 20%.
S104：If the matching degree meets preset requirement, first video file is recommended into the targeted customer.
Terminal confirm extracted from the second video file interesting element and the first interest information matching degree it is big
When preset matching degree threshold value, the first video file is recommended into targeted customer.Preset matching degree threshold value can basis
It is actually needed and is configured, is not limited herein.
Or terminal includes the first interest information correspondence in the interesting element of institute that confirmation is extracted from the second video file
Any interest when, the first video file is recommended into targeted customer.
It is understood that terminal is believed in the interesting element of institute and the first interest for confirming to extract from the second video file
The matching degree of breath is less than preset matching degree threshold value, or the interesting element of institute extracted from the second video file does not include first
During the corresponding any interest of interest information, the first video file will not be recommended to targeted customer.
Such scheme, terminal obtains the first interest information for the targeted customer for needing to obtain video information；By the of candidate
One video file is decomposed into the second video file, and the extraction interest element from second video file；Calculate the interest
The matching degree of element and first interest information；If the matching degree meets preset requirement, by first video file
Recommend the targeted customer.Because terminal is that the first video file is decomposed into at least two the second short video files, and
The video image of the second video file is analyzed, the interest element included in video image is therefrom extracted, can accurately know first
The corresponding interest element of video file, so as to the accurate recommended user of user video interested.
Fig. 2 is referred to, Fig. 2 is a kind of schematic flow diagram of the method for recommendation video that another embodiment of the present invention is provided.
The executive agent for recommending the method for video in the present embodiment is terminal, and terminal can play video.Terminal can be mobile phone, flat board
The mobile terminals such as computer, but this is not limited to, can also be other-end.The method of recommendation video as shown in Figure 2 may include
Following steps：
S201：Obtain the first interest information for the targeted customer for needing to obtain video information.
The S201 of the present embodiment is identical with the S101 in a upper embodiment, specifically refers to the tool of S101 in an embodiment
Body is described, and is not repeated herein.
S202：The first video file of candidate is decomposed into the second video file, and carried from second video file
Take interest element.
Terminal obtains the first video file of candidate from video library, and the first video file is decomposed into at least two
Two video files, and the video image that each second video file is included is analyzed, extract interest from each second video file
Element.
Wherein, the first video file is any one in video library；What at least two second video files were included regards
Frequency image can be spliced into the first video file.Interest element is the characteristic information that can be identified for that hobby.
Further, S202 can include S2021 and S2022, specific as follows：
S2021：The first video file of the candidate is decomposed into the second video file by preset frame rate.
Further, S2012 can include：If the first frame per second of first video file is more than the preset frame rate,
Then calculate the business of the first frame per second and the preset frame rate；Using the first number destination frame as resolving cell, by first video file
It is decomposed into the second video file；Wherein, first number is the business of first frame per second and the preset frame rate.
Wherein, each second can be more when frame per second is the frame number for showing or playing each second, i.e. graphics processor processing image
New number of times, the units of measurement of frame per second is to show frame number (Frames per Second, FPS) each second.Preset frame rate can root
Set according to the screen refresh rate of terminal display, because if preset frame rate exceedes the screen refresh rate of terminal, terminal is shown
Device can not update the image of display with preset frame rate, can waste the disposal ability of graphics processor.
For example, it is 24FPS (representing 24 width video images of refreshing per second or display) to work as preset frame rate, the first video file
When first frame per second is 72FPS, because the first frame per second 72FPS is more than preset frame rate 24FPS, terminal calculates the first frame per second and default frame
The business of rate：72/24=3.Terminal successively decomposes the video image of the first video file using 3 frame video images as resolving cell
Every continuous video image of 3 frame is taken to be second video file for multiple second video files, i.e. terminal.
It is understood that when the first frame per second not divisible preset frame rate of the first video file, i.e. the first video text
First frame per second of part is carried out after division arithmetic with preset frame rate, also remainder, be also using the business of the first frame per second and preset frame rate as
Resolving cell, operation splitting is carried out to the first video file.
Further, S2021 can also include：If the first frame per second of first video file is less than or equal to described pre-
If frame per second, then first video file is decomposed into by the second video file according to first frame per second.
When preset frame rate is 24FPS (representing 24 width video images of refreshing per second or display), the first of the first video file
When frame per second is 18FPS, because the first frame per second 18FPS is less than preset frame rate 24FPS, terminal is single using 18 frame video images to decompose
Member, is decomposed at least two second video files, i.e. terminal by the video image of the first video file successively and takes every 18 frame continuous
Video image be second video file.
When preset frame rate is 24FPS (representing 24 width video images of refreshing per second or display), the first of the first video file
When frame per second is 24FPS, because the first frame per second 24FPS is equal to preset frame rate 24FPS, terminal is single using 24 frame video images to decompose
Member, is decomposed at least two second video files, i.e. terminal by the video image of the first video file successively and takes every 24 frame continuous
Video image be second video file.
S2022：Interest element is extracted from second video file by default convolutional Neural net algorithm.
Default convolutional Neural net (Convolutional Neural Network, CNN) algorithm is：H (x)=(WiXi+
B)=(WTX), wherein, h (x) is the function on the second video file and interest element.I is the positive integer more than or equal to 1,
WiFor i-th of default known parameters, Xi is i-th of frame figure feature, and b is default constant.Frame figure feature corresponds to interest element.
Second video file can include an interest element, can also include at least two interest elements, not be limited herein.When
When two video files include at least two interest elements, any two interest element can be with identical, can also be different, does not do herein
Limitation.
In the present embodiment, convolutional Neural net is the convolutional Neural net connected entirely.Also referring to Fig. 3, Fig. 3 is the present invention
A kind of schematic diagram for convolutional Neural net connected entirely that embodiment is provided.
As shown in figure 3, the convolutional Neural net connected entirely includes input layer, hidden layer and output layer.Input layer, hidden layer
And between output layer be intercommunication.Comprising n element in input layer, during n is the positive integer more than or equal to 1, input layer
Arbitrary element is all connected with every element of hidden layer, and each element of hidden layer is all connected with output layer.
Wherein, what input layer was inputted is the frame figure of the second video file, and hidden layer mark intermediate processing results, output layer is defeated
What is gone out is the frame figure with frame figure feature.
Also referring to Fig. 4, Fig. 4 extracts the signal of characteristic element in being a kind of figure from frame provided in an embodiment of the present invention
Figure.
As shown in figure 4, terminal can extract frame figure from the second video file, one three layers of convolutional Neural net pair is used
Interest element in the frame figure of extraction carries out convolution, and interest element is obtained according to the frame figure feature of output.Frame figure feature in Fig. 4
For Kung Fu star's kick, terminal goes out the corresponding interest element of frame figure feature for action piece according to frame figure feature recognition
Element.Similarly, terminal can recognize other interest elements in the same way.
Wherein, terminal uses default convolutional Neural net algorithm h (x)=(WiXi+ b)=(WTX), using 2 × 2 convolution
Core (convolution feature) does convolution on frame figure n × n image, to extract interest element from the second video file.
Please refer to fig. 5, Fig. 5, which is one kind provided in an embodiment of the present invention, uses default convolutional Neural net algorithm to frame
Figure makees the schematic diagram of convolution.As shown in figure 5, terminal by the frame figure included in the second video file with 2 × 2 convolution kernel, from left
To the right side, convolution is done from top to bottom, and the frame figure feature extraction in two field picture is come out.Each convolution that terminal is done is a feature
Extract.
S203：Calculate the matching degree of the interest element and first interest information.
Also referring to Fig. 6, Fig. 6 is the signal of a kind of interest element provided in an embodiment of the present invention and the first interest information
Figure.
As shown in fig. 6, terminal can be by the first of the interest element extracted from the second video file and targeted customer
Interest information is compared, to judge whether the interest element extracted is consistent with the first interest information of targeted customer, so that
Obtain the matching degree of interest element and the first interest information of targeted customer.Matching degree can be percentage or specific
Fraction, be not limited herein.
For example, when the first interest information of targeted customer is comprising cartoon is liked, being extracted from the second video file
When interest element is cartoon element, the matching degree of the first interest information of terminal check interest element and targeted customer is
100%.
When the first interest information of targeted customer is comprising liking cartoon, liking certain substantially, carried from the second video file
When the interest element got is information (name or photograph of certain singer) of certain singer, terminal check interest element and targeted customer
The first interest information matching degree be 50%.
When the interest element extracted from the second video file does not include the first interest information of targeted customer, terminal
The matching degree for confirming interest element and the first interest information of targeted customer is zero, that is, the interest element extracted and the first interest
Information is mismatched.
When the first interest information at least two interest of correspondence of targeted customer, terminal can distribute weight to each interest
(can according to like degree to distribute weight), and confirming that the interest element that extracts includes corresponding of the first interest information
When interest is interesting, according to interest element and the weight of corresponding at least two interest of the first interest information, calculate interest element with
The matching degree of first interest information.
Wherein, terminal can like degree to distribute weight, happiness according to corresponding at least two interest of the first interest information
Joyous degree can be obtained from the search rate in historical viewing data or viewing number of times.
For example, when the first interest information of targeted customer includes " liking cartoon ", " liking certain obvious ", " liking animation
The corresponding weight of piece " is 0.8, and " liking certain obvious " corresponding weight is 0.2, the interest member extracted from the second video file
When element is information (name or photograph of certain singer) of certain singer, the first interest letter of terminal check interest element and targeted customer
The matching degree of breath is 20%.
Further, S203 can include：The interest element and first interest information are subjected to inner product operation, and
Calculate the summation of each inner product value；Wherein, the summation mark matching degree of the inner product value.
The interest element and the first interest information of extraction can be converted into bivector by terminal.For example, the first interest
Information (xi,yi), the corresponding vector of i-th of interest characteristics that the first interest information is included is represented, i is just whole more than or equal to 1
Number.Interest element (pj,qj), the corresponding vector of j-th of interest element is represented, j is also the positive integer more than or equal to 1.
Interest element and the first interest information are carried out into inner product operation to obtain：xipj+yiqj, and the table summed according to inner product
The summation of each inner product value is calculated up to formula.Wherein, the expression formula of inner product summation is：(x1p1+y1q1)+(x2p2+y2q2)+……+
(xipj+yiqj)。
Such as, the first interest information (liking action movie 1, Kung Fu star 1), (like singing star 1, sing the letter of star 1
Breath) ...；The interest element (action movie element 1, Kung Fu star 2) of extraction, (information of star 2 is sung, the name of star 2 is sung
Word) ... etc..
Terminal can be " (liking action movie 1, Kung Fu star 1) ", " (liking singing star 1, sing the information of star 1) "
Assignment, obtains the corresponding bivector of the first interest information；Can for extract interest element " (action movie element 1, acrobatic fighting is bright
Star 2) ", " (singing the information of star 2, sing the name of star 2) " carry out assignment, the interest element corresponding two extracted
Dimensional vector.Here, not limiting specific assignment, as long as meeting the requirement of bivector.
Similarly, terminal (can also own to the interest element extracted from the first video file after the same method
Each self-corresponding interest element of second video file) assignment is carried out, obtain corresponding bivector.
Further, when the number of the corresponding bivector of the first interest information is at least two, terminal can also be
The corresponding at least two bivectors distribution weight of first interest information.Wherein, terminal can be according to every in the first interest information
Individual bivector is corresponding to like degree to distribute weight, likes degree can be from the search rate in historical viewing data or viewing
Number of times is obtained.
S204：If the matching degree meets preset requirement, first video file is recommended into the targeted customer.
Terminal confirm extracted from the second video file interesting element and the first interest information matching degree it is big
When preset matching degree threshold value, the first video file is recommended into targeted customer.Preset matching degree threshold value can basis
It is actually needed and is configured, is not limited herein.
Or terminal includes the first interest information correspondence in the interesting element of institute that confirmation is extracted from the second video file
Any interest when, the first video file is recommended into targeted customer.
It is understood that terminal is believed in the interesting element of institute and the first interest for confirming to extract from the second video file
The matching degree of breath is less than preset matching degree threshold value, or the interesting element of institute extracted from the second video file does not include first
During the corresponding any interest of interest information, the first video file will not be recommended to targeted customer.
Further, the interest element and first interest information are being carried out inner product operation by terminal, and calculate each
During the summation of inner product value, S204 can include：If the summation of the inner product value is more than or equal to predetermined threshold value, by described first
Video file recommends the targeted customer.
Wherein, terminal is when confirming that calculating getable inner product summation is more than or equal to predetermined threshold value, by the first video text
Part recommends targeted customer；When confirming that calculating getable inner product summation is less than predetermined threshold value, do not recommend the to targeted customer
One video file.Predetermined threshold value can be true according to the assignment of the first interest information and each self-corresponding bivector of interest element
It is fixed, it is not limited herein.
Such scheme, terminal obtains the first interest information for the targeted customer for needing to obtain video information；By the of candidate
One video file is decomposed into the second video file, and the extraction interest element from second video file；Calculate the interest
The matching degree of element and first interest information；If the matching degree meets preset requirement, by first video file
Recommend the targeted customer.Because terminal is that the first video file is decomposed into at least two the second short video files, and
The video image of the second video file is analyzed, the interest element included in video image is therefrom extracted, can accurately know first
The corresponding interest element of video file, so as to the accurate recommended user of user video interested.
The first video file of candidate is decomposed into the second video file by terminal preset frame rate, passes through default convolutional Neural
Net algorithm extracts interest element from the second video file, and the interest element in frame figure can be recognized accurately, is pushed away so as to improve
Recommend the degree of accuracy of video.
Referring to Fig. 7, Fig. 7 is a kind of schematic block diagram of terminal provided in an embodiment of the present invention.Terminal can be mobile phone, put down
The mobile terminals such as plate computer, but this is not limited to, it can also be other-end, not be limited herein.The terminal 700 of the present embodiment
Including each unit be used to perform each step in the corresponding embodiments of Fig. 1, specifically refer to the corresponding implementations of Fig. 1 and Fig. 1
Associated description in example, is not repeated herein.The terminal of the present embodiment includes：Acquiring unit 710, extraction unit 720, computing unit
730 and recommendation unit 740.
Acquiring unit 710 is used for the first interest information for obtaining the targeted customer for needing to obtain video information.
Extraction unit 720 is used to the first video file of candidate being decomposed into the second video file, and is regarded from described second
Interest element is extracted in frequency file.
Computing unit 730 is used for the matching degree for calculating the interest element and first interest information.
If recommendation unit 740 meets preset requirement for the matching degree, first video file is recommended into institute
State targeted customer.
Such scheme, terminal obtains the first interest information for the targeted customer for needing to obtain video information；By the of candidate
One video file is decomposed into the second video file, and the extraction interest element from second video file；Calculate the interest
The matching degree of element and first interest information；If the matching degree meets preset requirement, by first video file
Recommend the targeted customer.Because terminal is that the first video file is decomposed into at least two the second short video files, and
The video image of the second video file is analyzed, the interest element included in video image is therefrom extracted, can accurately know first
The corresponding interest element of video file, so as to the accurate recommended user of user video interested.
Referring to Fig. 8, Fig. 8 is a kind of schematic block diagram for terminal that another embodiment of the present invention is provided.Terminal can be hand
The mobile terminals such as machine, tablet personal computer, but this is not limited to, it can also be other-end, not be limited herein.The end of the present embodiment
The each unit that end 800 includes is used to perform each step in the corresponding embodiments of Fig. 2, specifically refers to Fig. 2 and Fig. 2 is corresponding
Associated description in embodiment, is not repeated herein.The terminal of the present embodiment includes：Acquiring unit 810, extraction unit 820, calculating
Unit 830 and recommendation unit 840.Wherein, extraction unit 820 can include resolving cell 821 and interest element extraction list
Member 822.
Acquiring unit 810 is used for the first interest information for obtaining the targeted customer for needing to obtain video information.
Extraction unit 820 is used to the first video file of candidate being decomposed into the second video file, and is regarded from described second
Interest element is extracted in frequency file.
Further, when extraction unit 820 includes resolving cell 821 and interest element extraction unit 822, decompose single
Member 821 is used to the first video file of the candidate is decomposed into the second video file by preset frame rate；Interest element extraction list
Member 822 is used to extract interest element from second video file by default convolutional Neural net algorithm.
Further, if resolving cell 821 is more than described preset specifically for the first frame per second of first video file
Frame per second, then calculate the business of the first frame per second and the preset frame rate；Using the first number destination frame as resolving cell, by first video
File is decomposed into the second video file；Wherein, first number is the business of first frame per second and the preset frame rate.
Further, if resolving cell 821 is additionally operable to the first frame per second of first video file less than or equal to described
Preset frame rate, then be decomposed into the second video file according to first frame per second by first video file.
Computing unit 830 is used for the matching degree for calculating the interest element and first interest information.
Further, computing unit 830 by the interest element and first interest information specifically for carrying out inner product
Computing, and calculate the summation of each inner product value；Wherein, the summation mark matching degree of the inner product value.
If recommendation unit 840 meets preset requirement for the matching degree, first video file is recommended into institute
State targeted customer.
Further, when computing unit 830 calculate obtain the summation of each inner product value when, if recommendation unit 840 specifically for
The summation of the inner product value is more than or equal to predetermined threshold value, then first video file is recommended into the targeted customer.
Such scheme, terminal obtains the first interest information for the targeted customer for needing to obtain video information；By the of candidate
One video file is decomposed into the second video file, and the extraction interest element from second video file；Calculate the interest
The matching degree of element and first interest information；If the matching degree meets preset requirement, by first video file
Recommend the targeted customer.Because terminal is that the first video file is decomposed into at least two the second short video files, and
The video image of the second video file is analyzed, the interest element included in video image is therefrom extracted, can accurately know first
The corresponding interest element of video file, so as to the accurate recommended user of user video interested.
The first video file of candidate is decomposed into the second video file by terminal preset frame rate, passes through default convolutional Neural
Net algorithm extracts interest element from the second video file, and the interest element in frame figure can be recognized accurately, is pushed away so as to improve
Recommend the degree of accuracy of video.
Referring to Fig. 9, Fig. 9 is a kind of terminal schematic block diagram that yet another embodiment of the invention is provided.This implementation as shown in Figure 6
Terminal 900 in example can include：One or more processors 910；One or more input equipments 920, it is one or more defeated
Go out equipment 930 and memory 940.Above-mentioned processor 910, input equipment 920, output equipment 930 and memory 940 pass through bus
950 connections.
Memory 940 is instructed for storage program.
The programmed instruction that processor 910 is used to be stored according to memory 940 performs following operate：
Processor 910 is used for the first interest information for obtaining the targeted customer for needing to obtain video information；
Processor 910 is additionally operable to the first video file of candidate being decomposed into the second video file, and is regarded from described second
Interest element is extracted in frequency file；
Processor 910 is additionally operable to calculate the matching degree of the interest element and first interest information；
If processor 910, which is additionally operable to the matching degree, meets preset requirement, first video file is recommended into institute
State targeted customer.
Further, processor 910 by the first video file of the candidate by preset frame rate specifically for being decomposed into
Two video files；Interest element is extracted from second video file by default convolutional Neural net algorithm.
Further, processor 910 by the interest element and first interest information specifically for carrying out inner product fortune
Calculate, and calculate the summation of each inner product value；Wherein, the summation mark matching degree of the inner product value；If the summation of the inner product value is big
In or equal to predetermined threshold value, then first video file is recommended into the targeted customer.
Further, if processor 910 is more than the default frame specifically for the first frame per second of first video file
Rate, then calculate the business of the first frame per second and the preset frame rate；Using the first number destination frame as resolving cell, by first video text
Part is decomposed into the second video file；Wherein, first number is the business of first frame per second and the preset frame rate.
Further, if processor 910 is additionally operable to the first frame per second of first video file less than or equal to described pre-
If frame per second, then first video file is decomposed into by the second video file according to first frame per second.
Such scheme, terminal obtains the first interest information for the targeted customer for needing to obtain video information；By the of candidate
One video file is decomposed into the second video file, and the extraction interest element from second video file；Calculate the interest
The matching degree of element and first interest information；If the matching degree meets preset requirement, by first video file
Recommend the targeted customer.Because terminal is that the first video file is decomposed into at least two the second short video files, and
The video image of the second video file is analyzed, the interest element included in video image is therefrom extracted, can accurately know first
The corresponding interest element of video file, so as to the accurate recommended user of user video interested.
The first video file of candidate is decomposed into the second video file by terminal preset frame rate, passes through default convolutional Neural
Net algorithm extracts interest element from the second video file, and the interest element in frame figure can be recognized accurately, is pushed away so as to improve
Recommend the degree of accuracy of video.
It should be appreciated that in embodiments of the present invention, alleged processor 910 can be CPU (Central
Processing Unit, CPU), the processor can also be other general processors, digital signal processor (Digital
Signal Processor, DSP), application specific integrated circuit (Application Specific Integrated Circuit,
ASIC), ready-made programmable gate array (Field-Programmable Gate Array, FPGA) or other FPGAs
Device, discrete gate or transistor logic, discrete hardware components etc..General processor can be microprocessor or this at
It can also be any conventional processor etc. to manage device.
Input equipment 920 can include Trackpad, fingerprint adopt sensor (finger print information that is used to gathering user and fingerprint
Directional information), microphone etc., output equipment 930 can include display (LCD etc.), loudspeaker etc..
The memory 940 can include read-only storage and random access memory, and to processor 910 provide instruction and
Data.The a part of of memory 940 can also include nonvolatile RAM.For example, memory 940 can also be deposited
Store up the information of device type.
In the specific implementation, processor 910, input equipment 920, the output equipment 930 described in the embodiment of the present invention can
Perform the realization side described in the first embodiment and second embodiment of the method provided in an embodiment of the present invention for recommending video
Formula, also can perform the implementation of the terminal described by the embodiment of the present invention, will not be repeated here.
Those of ordinary skill in the art are it is to be appreciated that the list of each example described with reference to the embodiments described herein
Member and algorithm steps, can be realized with electronic hardware, computer software or the combination of the two, in order to clearly demonstrate hardware
With the interchangeability of software, the composition and step of each example are generally described according to function in the above description.This
A little functions are performed with hardware or software mode actually, depending on the application-specific and design constraint of technical scheme.Specially
Industry technical staff can realize described function to each specific application using distinct methods, but this realization is not
It is considered as beyond the scope of this invention.
It is apparent to those skilled in the art that, for convenience of description and succinctly, the end of foregoing description
End and the specific work process of unit, may be referred to the corresponding process in preceding method embodiment, will not be repeated here.
, can be by it in several embodiments provided herein, it should be understood that disclosed terminal and method
Its mode is realized.For example, device embodiment described above is only schematical, for example, the division of the unit, only
Only a kind of division of logic function, can there is other dividing mode when actually realizing, such as multiple units or component can be tied
Another system is closed or is desirably integrated into, or some features can be ignored, or do not perform.In addition, shown or discussed phase
Coupling or direct-coupling or communication connection between mutually can be INDIRECT COUPLING or the communication by some interfaces, device or unit
Connection or electricity, mechanical or other forms are connected.
Step in present invention method can be sequentially adjusted, merged and deleted according to actual needs.
Unit in terminal of the embodiment of the present invention can be combined, divided and deleted according to actual needs.
The unit illustrated as separating component can be or may not be it is physically separate, it is aobvious as unit
The part shown can be or may not be physical location, you can with positioned at a place, or can also be distributed to multiple
On NE.Some or all of unit therein can be selected to realize scheme of the embodiment of the present invention according to the actual needs
Purpose.
In addition, each functional unit in each embodiment of the invention can be integrated in a processing unit, can also
It is that unit is individually physically present or two or more units are integrated in a unit.It is above-mentioned integrated
Unit can both be realized in the form of hardware, it would however also be possible to employ the form of SFU software functional unit is realized.
If the integrated unit is realized using in the form of SFU software functional unit and as independent production marketing or used
When, it can be stored in a computer read/write memory medium.Understood based on such, technical scheme is substantially
The part contributed in other words to prior art, or all or part of the technical scheme can be in the form of software product
Embody, the computer software product is stored in a storage medium, including some instructions are to cause a computer
Equipment (can be personal computer, server, or network equipment etc.) performs the complete of each embodiment methods described of the invention
Portion or part steps.And foregoing storage medium includes：USB flash disk, mobile hard disk, read-only storage (ROM, Read-Only
Memory), random access memory (RAM, Random Access Memory), magnetic disc or CD etc. are various can store journey
The medium of sequence code.
The foregoing is only a specific embodiment of the invention, but protection scope of the present invention is not limited thereto, any
Those familiar with the art the invention discloses technical scope in, various equivalent modifications can be readily occurred in or replaced
Change, these modifications or substitutions should be all included within the scope of the present invention.Therefore, protection scope of the present invention should be with right
It is required that protection domain be defined.
Claims (10)
1. a kind of method of recommendation video, it is characterised in that methods described includes：
Obtain the first interest information for the targeted customer for needing to obtain video information；
The first video file of candidate is decomposed into the second video file, and the extraction interest member from second video file
Element；
Calculate the matching degree of the interest element and first interest information；
If the matching degree meets preset requirement, first video file is recommended into the targeted customer.
2. according to the method described in claim 1, it is characterised in that described the first video file of candidate is decomposed into second to regard
Frequency file, and extraction interest element includes from second video file：
The first video file of the candidate is decomposed into the second video file by preset frame rate；
Interest element is extracted from second video file by default convolutional Neural net algorithm.
3. method according to claim 1 or 2, it is characterised in that the calculating interest element is used with the target
The matching degree of the interest information at family includes：
The interest element and first interest information are subjected to inner product operation, and calculate the summation of each inner product value；Wherein, institute
State the summation mark matching degree of inner product value；
If the matching degree meets preset requirement, first video file is recommended into the targeted customer, including：
If the summation of the inner product value is more than or equal to predetermined threshold value, first video file is recommended into the target and used
Family.
4. method according to claim 2, it is characterised in that described by preset frame rate that the first video of the candidate is literary
Part, which is decomposed into the second video file, to be included：
If the first frame per second of first video file is more than the preset frame rate, the first frame per second and the preset frame rate are calculated
Business；
Using the first number destination frame as resolving cell, first video file is decomposed into the second video file；Wherein, described
One number is the business of first frame per second and the preset frame rate.
5. method according to claim 2, it is characterised in that described by preset frame rate that the first video of the candidate is literary
Part, which is decomposed into the second video file, to be included：
If the first frame per second of first video file is less than or equal to the preset frame rate, according to first frame per second by institute
State the first video file and be decomposed into the second video file.
6. a kind of terminal, it is characterised in that the terminal includes：
Acquiring unit, the first interest information for obtaining the targeted customer for needing to obtain video information；
Extraction unit, for the first video file of candidate to be decomposed into the second video file, and from second video file
Middle extraction interest element；
Computing unit, the matching degree for calculating the interest element and first interest information；
Recommendation unit, if meeting preset requirement for the matching degree, the target is recommended by first video file
User.
7. terminal according to claim 6, it is characterised in that the extraction unit includes：
Resolving cell, for the first video file of the candidate to be decomposed into the second video file by preset frame rate；
Interest element extraction unit, for extracting interest from second video file by default convolutional Neural net algorithm
Element.
8. the terminal according to claim 6 or 7, it is characterised in that
The computing unit calculates each specifically for the interest element and first interest information are carried out into inner product operation
The summation of inner product value；Wherein, the summation mark matching degree of the inner product value；
If the recommendation unit is more than or equal to predetermined threshold value specifically for the summation of the inner product value, by first video
File recommendation gives the targeted customer.
9. terminal according to claim 7, it is characterised in that if the resolving cell is specifically for first video text
First frame per second of part is more than the preset frame rate, then calculates the business of the first frame per second and the preset frame rate；With the first number destination frame
For resolving cell, first video file is decomposed into the second video file；Wherein, first number is first frame
The business of rate and the preset frame rate.
10. terminal according to claim 7, it is characterised in that if the resolving cell is additionally operable to the first video text
First frame per second of part is less than or equal to the preset frame rate, then is decomposed into first video file according to first frame per second
Second video file.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710164492.1A CN106993226A (en) | 2017-03-17 | 2017-03-17 | A kind of method and terminal of recommendation video |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710164492.1A CN106993226A (en) | 2017-03-17 | 2017-03-17 | A kind of method and terminal of recommendation video |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106993226A true CN106993226A (en) | 2017-07-28 |
Family
ID=59413297
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710164492.1A Withdrawn CN106993226A (en) | 2017-03-17 | 2017-03-17 | A kind of method and terminal of recommendation video |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106993226A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109874053A (en) * | 2019-02-21 | 2019-06-11 | 南京航空航天大学 | The short video recommendation method with user's dynamic interest is understood based on video content |
| CN109922356A (en) * | 2019-03-01 | 2019-06-21 | 广州酷狗计算机科技有限公司 | Video recommendation method, device and computer readable storage medium |
| CN109992678A (en) * | 2019-03-14 | 2019-07-09 | 深圳市腾讯计算机系统有限公司 | The determination method and device of destination multimedia file |
| CN112000819A (en) * | 2019-05-27 | 2020-11-27 | 北京达佳互联信息技术有限公司 | Multimedia resource recommendation method and device, electronic equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104966104A (en) * | 2015-06-30 | 2015-10-07 | 孙建德 | Three-dimensional convolutional neural network based video classifying method |
| CN105847985A (en) * | 2016-03-30 | 2016-08-10 | 乐视控股（北京）有限公司 | Video recommendation method and device |
| CN105930425A (en) * | 2016-04-18 | 2016-09-07 | 乐视控股（北京）有限公司 | Personalized video recommendation method and apparatus |
| CN106202475A (en) * | 2016-07-18 | 2016-12-07 | 合网络技术（北京）有限公司 | The method for pushing of a kind of video recommendations list and device |
| CN108227950A (en) * | 2016-12-21 | 2018-06-29 | 北京搜狗科技发展有限公司 | A kind of input method and device |
-
2017
- 2017-03-17 CN CN201710164492.1A patent/CN106993226A/en not_active Withdrawn
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104966104A (en) * | 2015-06-30 | 2015-10-07 | 孙建德 | Three-dimensional convolutional neural network based video classifying method |
| CN105847985A (en) * | 2016-03-30 | 2016-08-10 | 乐视控股（北京）有限公司 | Video recommendation method and device |
| CN105930425A (en) * | 2016-04-18 | 2016-09-07 | 乐视控股（北京）有限公司 | Personalized video recommendation method and apparatus |
| CN106202475A (en) * | 2016-07-18 | 2016-12-07 | 合网络技术（北京）有限公司 | The method for pushing of a kind of video recommendations list and device |
| CN108227950A (en) * | 2016-12-21 | 2018-06-29 | 北京搜狗科技发展有限公司 | A kind of input method and device |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109874053A (en) * | 2019-02-21 | 2019-06-11 | 南京航空航天大学 | The short video recommendation method with user's dynamic interest is understood based on video content |
| CN109922356A (en) * | 2019-03-01 | 2019-06-21 | 广州酷狗计算机科技有限公司 | Video recommendation method, device and computer readable storage medium |
| CN109922356B (en) * | 2019-03-01 | 2021-07-09 | 广州酷狗计算机科技有限公司 | Video recommendation method and device and computer-readable storage medium |
| CN109992678A (en) * | 2019-03-14 | 2019-07-09 | 深圳市腾讯计算机系统有限公司 | The determination method and device of destination multimedia file |
| CN109992678B (en) * | 2019-03-14 | 2021-05-11 | 深圳市腾讯计算机系统有限公司 | Method and device for determining target multimedia file |
| CN112000819A (en) * | 2019-05-27 | 2020-11-27 | 北京达佳互联信息技术有限公司 | Multimedia resource recommendation method and device, electronic equipment and storage medium |
| CN112000819B (en) * | 2019-05-27 | 2023-07-11 | 北京达佳互联信息技术有限公司 | Multimedia resource recommendation method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9569536B2 (en) | Identifying similar applications | |
| CN105229575B (en) | Text prediction based on multiple language models | |
| US10007933B2 (en) | Systems and methods for integrating dynamic content into electronic media | |
| CN110020188A (en) | Recommended based on the Global Vector of implicit interactions and profile data | |
| CN107729937A (en) | For determining the method and device of user interest label | |
| JP6316883B2 (en) | Messaging application-based advertisement providing method and advertisement providing system | |
| CN111597006A (en) | Application split screen method and device, storage medium and electronic equipment | |
| CN107526810B (en) | Method and device for establishing click rate estimation model and display method and device | |
| CN105283839A (en) | Personalized community model for surfacing commands within productivity application user interfaces | |
| CN106993226A (en) | A kind of method and terminal of recommendation video | |
| WO2015196467A1 (en) | Automated click type selection for content performance optimization | |
| US20100177122A1 (en) | Video-Associated Objects | |
| US9542458B2 (en) | Systems and methods for processing and displaying user-generated content | |
| CN112528007B (en) | Confirmation method and confirmation device for target enterprise of business inviting project | |
| CN110321469A (en) | The embedding media content item in the text of electronic document | |
| CN107205042A (en) | A kind of accurate information method for pushing and system | |
| CN107666435A (en) | A kind of method and device for shielding message | |
| CN106921724A (en) | Game promotion content processing method and device | |
| CN111461801A (en) | Page generation method and device | |
| CN110020132B (en) | Keyword recommendation method and device, computing equipment and storage medium | |
| Kim et al. | Emotion-based Hangul font recommendation system using crowdsourcing | |
| WO2019133164A1 (en) | System and method for recommending features for content presentations | |
| CN115115074A (en) | Electronic resource consumption information prediction method, device, equipment and storage medium | |
| CN111369324A (en) | Target information determination method, device, equipment and readable storage medium | |
| CN112328339B (en) | Notification message display method and device, storage medium and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20170728 |